AI agents call get_likes to retrieve information from YouTube MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves likes count from YouTube videos, which is querying public metadata without side effects. The empty description lowers confidence slightly, but the name and server context (analyzing YouTube videos) strongly suggest this is a read-only operation to fetch engagement metrics. This aligns with similar sibling tools like get_comments and get_transcript that extract video information.
From the tool's definition Tool name 'get_likes' and server context indicating it retrieves YouTube video data (similar to sibling tools get_transcript, get_comments which are read operations on public video metadata).
Documented attack patterns abuse exactly the kind of access get_likes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and YouTube MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_likes:
{
"version": "1",
"default": "deny",
"tools": {
"get_likes": {}
}
}get_likes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_likes. It is categorised as a Read tool in the YouTube MCP MCP Server, which means it retrieves data without modifying state.
Register the YouTube MCP server in PolicyLayer and add a rule for get_likes: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches YouTube MCP. Nothing to install.
get_likes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_likes rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_likes. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_likes is provided by the YouTube MCP server (prajwal-ak-0/youtube-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from YouTube MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 YouTube MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.